{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","short_pith_number":"pith:SAOT6P6Z","schema_version":"1.0","canonical_sha256":"901d3f3fd991760e993f0749ba42d9d0640408f60d2864cf090f0763ec0fa536","source":{"kind":"arxiv","id":"2608.07435","version":1},"attestation_state":"computed","paper":{"title":"SABRE: Scalable and Automated Benchmarking of VLMs under Stress","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiawei Zhou, Luzhe Sun, Matthew R. Walter, Zixuan Lan","submitted_at":"2026-08-07T17:21:04Z","abstract_excerpt":"Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and question-answer pairs. Automated filtering removes candidates solved by a Filtering VLM, while human review verifies candidate validity and supports annotation cor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.07435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T17:21:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"66dd2e97f35d39c1b88311544b7f31d9bb8b94d4bddb70495d31b421914a5065","abstract_canon_sha256":"4d825d641e25f0ddaaefd36be87a3ab6b7836a13ec2bb3ef1b4da5693f58fe04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:23.314441Z","signature_b64":"xamfYwKCp39hCMAXotXN3yt7Cw9MhqeqliJdGfQB8GFNXpXLGkhQu2Mk2/srPgb+KfI/4MxQGMN5F/aeAvuSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"901d3f3fd991760e993f0749ba42d9d0640408f60d2864cf090f0763ec0fa536","last_reissued_at":"2026-08-10T01:15:23.311904Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:23.311904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SABRE: Scalable and Automated Benchmarking of VLMs under Stress","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiawei Zhou, Luzhe Sun, Matthew R. Walter, Zixuan Lan","submitted_at":"2026-08-07T17:21:04Z","abstract_excerpt":"Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and question-answer pairs. Automated filtering removes candidates solved by a Filtering VLM, while human review verifies candidate validity and supports annotation cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07435","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.07435/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.07435","created_at":"2026-08-10T01:15:23.312868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07435v1","created_at":"2026-08-10T01:15:23.312868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07435","created_at":"2026-08-10T01:15:23.312868+00:00"},{"alias_kind":"pith_short_12","alias_value":"SAOT6P6ZSF3A","created_at":"2026-08-10T01:15:23.312868+00:00"},{"alias_kind":"pith_short_16","alias_value":"SAOT6P6ZSF3A5GJ7","created_at":"2026-08-10T01:15:23.312868+00:00"},{"alias_kind":"pith_short_8","alias_value":"SAOT6P6Z","created_at":"2026-08-10T01:15:23.312868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","json":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B.json","graph_json":"https://pith.science/api/pith-number/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/graph.json","events_json":"https://pith.science/api/pith-number/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/events.json","paper":"https://pith.science/paper/SAOT6P6Z"},"agent_actions":{"view_html":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","download_json":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B.json","view_paper":"https://pith.science/paper/SAOT6P6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07435&json=true","fetch_graph":"https://pith.science/api/pith-number/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/graph.json","fetch_events":"https://pith.science/api/pith-number/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/action/storage_attestation","attest_author":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/action/author_attestation","sign_citation":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/action/citation_signature","submit_replication":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/action/replication_record"}},"created_at":"2026-08-10T01:15:23.312868+00:00","updated_at":"2026-08-10T01:15:23.312868+00:00"}